{"total":201,"rows":[{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"area":null},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28,"area":null},{"id":"2509.26618","title":"DA$^{2}$: Depth Anything in Any Direction","created":"2025-09-30","cited_by_count":25,"area":null},{"id":"2512.16913","title":"Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation","created":"2025-12-18","cited_by_count":25,"area":null},{"id":"2601.03252","title":"InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields","created":"2026-01-06","cited_by_count":23,"area":null},{"id":"2603.05449","title":"RealWonder: Real-Time Physical Action-Conditioned Video Generation","created":"2026-03-05","cited_by_count":22,"area":null},{"id":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21,"area":null},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2604.21915","title":"Vista4D: Video Reshooting with 4D Point Clouds","created":"2026-04-23","cited_by_count":18,"area":null},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2606.19333","title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","created":"2026-06-17","cited_by_count":13,"area":null},{"id":"2509.02530","title":"Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots","created":"2025-09-02","cited_by_count":11,"area":null},{"id":"2602.09013","title":"Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2604.04135","title":"NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results","created":"2026-04-05","cited_by_count":11,"area":null},{"id":"2604.04406","title":"3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2511.04595","title":"UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction","created":"2025-11-06","cited_by_count":10,"area":null},{"id":"2510.10287","title":"Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2512.08269","title":"EgoX: Egocentric Video Generation from a Single Exocentric Video","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2602.20119","title":"NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2603.27105","title":"UniDAC: Universal Metric Depth Estimation for Any Camera","created":"2026-03-28","cited_by_count":8,"area":null},{"id":"2607.17967","title":"MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement","created":"2026-07-20","cited_by_count":8,"area":null},{"id":"2509.24209","title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2512.22854","title":"ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2510.06469","title":"SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2602.05330","title":"MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2602.23893","title":"AoE: Always-on Egocentric Human Video Collection for Embodied AI","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2603.05711","title":"Any to Full: Prompting Depth Anything for Depth Completion in One Stage","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2603.29387","title":"Extend3D: Town-Scale 3D Generation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2510.24464","title":"Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.15603","title":"Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2603.17355","title":"OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2605.30115","title":"Large Depth Completion Model from Sparse Observations","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.13676","title":"Modality Forcing for Scalable Spatial Generation","created":"2026-06-11","cited_by_count":4,"area":null},{"id":"2602.14751","title":"Depth Completion as Parameter-Efficient Test-Time Adaptation","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2602.18906","title":"Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates","created":"2026-02-21","cited_by_count":3,"area":null},{"id":"2603.01765","title":"StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.03744","title":"DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2605.20992","title":"Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2605.25308","title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.21596","title":"$\\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction","created":"2026-06-19","cited_by_count":3,"area":null},{"id":"2606.29716","title":"AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2607.01015","title":"SuperFlex: Deformable Superquadrics for Point Cloud Decomposition","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.11588","title":"FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry","created":"2026-07-13","cited_by_count":3,"area":null},{"id":"2607.12993","title":"X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2507.11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2510.17157","title":"GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2511.17340","title":"Refracting Reality: Generating Images with Realistic Transparent Objects","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2511.19172","title":"MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2512.10959","title":"StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2512.22819","title":"Depth Anything in $360^\\circ$: Towards Scale Invariance in the Wild","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2601.03362","title":"Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2601.05246","title":"Pixel-Perfect Visual Geometry Estimation","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2602.00839","title":"TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.01007","title":"Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.03765","title":"LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.11047","title":"LiTo: Surface Light Field Tokenization","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.19547","title":"SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2603.25539","title":"PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2603.25726","title":"AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2604.19624","title":"GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2605.17354","title":"GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.31577","title":"SurGe: Improved Surface Geometry in Point Maps","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2605.31595","title":"Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.02417","title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2608.20534","title":"Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2609.04958","title":"MINT: A Unified Model for World-Space Camera and Hand Motion Estimation from Scalable Egocentric Pipeline Supervision","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2508.12349","title":"EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2510.19814","title":"Toward A Better Understanding of Monocular Depth Evaluation","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2511.13015","title":"Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cues","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.04303","title":"Gamma-from-Mono: Road-Relative, Metric, Self-Supervised Monocular Geometry for Vehicular Applications","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2512.09583","title":"UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2512.12425","title":"Boosting Monocular Metric Depth Estimation via Bokeh Rendering","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.01188","title":"DST-Calib: A Dual-Path, Self-Supervised, Target-Free LiDAR-Camera Extrinsic Calibration Network","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2601.12729","title":"DC-VLAQ: Query-Residual Aggregation for Robust Visual Place Recognition","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.01296","title":"Interacted Planes Reveal 3D Line Mapping","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2603.16816","title":"WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.29368","title":"StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.05359","title":"GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.05715","title":"In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.09352","title":"LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.05014","title":"CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.11594","title":"PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.12774","title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.26456","title":"Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.13497","title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.13644","title":"Surflo: Consistent 3D Surface Flow Model with Global State","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.16960","title":"SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.25245","title":"OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos","created":"2026-06-24","cited_by_count":1,"area":null}],"next_cursor":"100"}